Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network

05/09/2021
by   Hong-Ye Zeng, et al.
0

Objective: The spinous process angle (SPA) is one of the essential parameters to denote three-dimensional (3-D) deformity of spine. We propose an automatic segmentation method based on Stacked Hourglass Network (SHN) to detect the spinous processes (SP) on ultrasound (US) spine images and to measure the SPAs of clinical scoliotic subjects. Methods: The network was trained to detect vertebral SP and laminae as five landmarks on 1200 ultrasound transverse images and validated on 100 images. All the processed transverse images with highlighted SP and laminae were reconstructed into a 3D image volume, and the SPAs were measured on the projected coronal images. The trained network was tested on 400 images by calculating the percentage of correct keypoints (PCK); and the SPA measurements were evaluated on 50 scoliotic subjects by comparing the results from US images and radiographs. Results: The trained network achieved a high average PCK (86.8 of SP detection was 90.3 showed good correlation (r>0.85), and the mean absolute differences (MAD) between two modalities were 3.3, which was less than the clinical acceptance error (5). Conclusion: The vertebral features can be accurately segmented on US spine images using SHN, and the measurement results of SPA from US data was comparable to the gold standard from radiography.

READ FULL TEXT

page 2

page 4

page 5

page 7

page 8

research
04/17/2022

Automatic spinal curvature measurement on ultrasound spine images using Faster R-CNN

Ultrasound spine imaging technique has been applied to the assessment of...
research
01/28/2022

Carotid artery wall segmentation in ultrasound image sequences using a deep convolutional neural network

The objective of this study is the segmentation of the intima-media comp...
research
06/28/2017

The application of deep convolutional neural networks to ultrasound for modelling of dynamic states within human skeletal muscle

This paper concerns the fully automatic direct in vivo measurement of ac...
research
08/15/2023

Deep Learning Framework for Spleen Volume Estimation from 2D Cross-sectional Views

Abnormal spleen enlargement (splenomegaly) is regarded as a clinical ind...
research
05/18/2021

Assessing aesthetics of generated abstract images using correlation structure

Can we generate abstract aesthetic images without bias from natural or h...
research
06/11/2017

A dynamic graph-cuts method with integrated multiple feature maps for segmenting kidneys in ultrasound images

Purpose: To improve kidney segmentation in clinical ultrasound (US) imag...
research
11/22/2019

Shape Detection In 2D Ultrasound Images

Ultrasound images are one of the most widely used techniques in clinical...

Please sign up or login with your details

Forgot password? Click here to reset